Multi-Horizon Air Pollution Forecasting with Deep Neural Networks
Air pollution is a global problem, especially in urban areas where the population density is very high due to the diverse pollutant sources such as vehicles, industrial plants, buildings, and waste. North Macedonia, as a developing country, has a serious problem with air pollution. The problem is hi...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/4/1235 |
id |
doaj-edb231fdf5d242bbada5ae176b272da5 |
---|---|
record_format |
Article |
spelling |
doaj-edb231fdf5d242bbada5ae176b272da52021-02-11T00:00:04ZengMDPI AGSensors1424-82202021-02-01211235123510.3390/s21041235Multi-Horizon Air Pollution Forecasting with Deep Neural NetworksMirche Arsov0Eftim Zdravevski1Petre Lameski2Roberto Corizzo3Nikola Koteli4Sasho Gramatikov5Kosta Mitreski6Vladimir Trajkovik7Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North MacedoniaFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North MacedoniaFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North MacedoniaDepartment of Computer Science, American University, Washington, DC 20016, USAFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North MacedoniaFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North MacedoniaFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North MacedoniaFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North MacedoniaAir pollution is a global problem, especially in urban areas where the population density is very high due to the diverse pollutant sources such as vehicles, industrial plants, buildings, and waste. North Macedonia, as a developing country, has a serious problem with air pollution. The problem is highly present in its capital city, Skopje, where air pollution places it consistently within the top 10 cities in the world during the winter months. In this work, we propose using Recurrent Neural Network (RNN) models with long short-term memory units to predict the level of PM10 particles at 6, 12, and 24 h in the future. We employ historical air quality measurement data from sensors placed at multiple locations in Skopje and meteorological conditions such as temperature and humidity. We compare different deep learning models’ performance to an Auto-regressive Integrated Moving Average (ARIMA) model. The obtained results show that the proposed models consistently outperform the baseline model and can be successfully employed for air pollution prediction. Ultimately, we demonstrate that these models can help decision-makers and local authorities better manage the air pollution consequences by taking proactive measures.https://www.mdpi.com/1424-8220/21/4/1235RNNLSTMconvolutional networksdeep learningair pollution |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mirche Arsov Eftim Zdravevski Petre Lameski Roberto Corizzo Nikola Koteli Sasho Gramatikov Kosta Mitreski Vladimir Trajkovik |
spellingShingle |
Mirche Arsov Eftim Zdravevski Petre Lameski Roberto Corizzo Nikola Koteli Sasho Gramatikov Kosta Mitreski Vladimir Trajkovik Multi-Horizon Air Pollution Forecasting with Deep Neural Networks Sensors RNN LSTM convolutional networks deep learning air pollution |
author_facet |
Mirche Arsov Eftim Zdravevski Petre Lameski Roberto Corizzo Nikola Koteli Sasho Gramatikov Kosta Mitreski Vladimir Trajkovik |
author_sort |
Mirche Arsov |
title |
Multi-Horizon Air Pollution Forecasting with Deep Neural Networks |
title_short |
Multi-Horizon Air Pollution Forecasting with Deep Neural Networks |
title_full |
Multi-Horizon Air Pollution Forecasting with Deep Neural Networks |
title_fullStr |
Multi-Horizon Air Pollution Forecasting with Deep Neural Networks |
title_full_unstemmed |
Multi-Horizon Air Pollution Forecasting with Deep Neural Networks |
title_sort |
multi-horizon air pollution forecasting with deep neural networks |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-02-01 |
description |
Air pollution is a global problem, especially in urban areas where the population density is very high due to the diverse pollutant sources such as vehicles, industrial plants, buildings, and waste. North Macedonia, as a developing country, has a serious problem with air pollution. The problem is highly present in its capital city, Skopje, where air pollution places it consistently within the top 10 cities in the world during the winter months. In this work, we propose using Recurrent Neural Network (RNN) models with long short-term memory units to predict the level of PM10 particles at 6, 12, and 24 h in the future. We employ historical air quality measurement data from sensors placed at multiple locations in Skopje and meteorological conditions such as temperature and humidity. We compare different deep learning models’ performance to an Auto-regressive Integrated Moving Average (ARIMA) model. The obtained results show that the proposed models consistently outperform the baseline model and can be successfully employed for air pollution prediction. Ultimately, we demonstrate that these models can help decision-makers and local authorities better manage the air pollution consequences by taking proactive measures. |
topic |
RNN LSTM convolutional networks deep learning air pollution |
url |
https://www.mdpi.com/1424-8220/21/4/1235 |
work_keys_str_mv |
AT mirchearsov multihorizonairpollutionforecastingwithdeepneuralnetworks AT eftimzdravevski multihorizonairpollutionforecastingwithdeepneuralnetworks AT petrelameski multihorizonairpollutionforecastingwithdeepneuralnetworks AT robertocorizzo multihorizonairpollutionforecastingwithdeepneuralnetworks AT nikolakoteli multihorizonairpollutionforecastingwithdeepneuralnetworks AT sashogramatikov multihorizonairpollutionforecastingwithdeepneuralnetworks AT kostamitreski multihorizonairpollutionforecastingwithdeepneuralnetworks AT vladimirtrajkovik multihorizonairpollutionforecastingwithdeepneuralnetworks |
_version_ |
1724275014888325120 |